Origins
Carried from docs/origins.md on 30 Sept 2026; the file is the source.
Origins
Where Vishy came from, and where each step is written down. Everything below is in this repository; the dates are the days the work happened.
The idea
A thought experiment on 25 Sept 2026: a software factory in which many AI agents write one program at the same time. Every attempt at that stalls in the same places, because in ordinary languages the piece of work an agent gets is not a boundary. Agents reach into each other’s state, duplicate helpers, hold different assumptions, and every disagreement surfaces at integration, serially, in merge conflicts. The conclusion was that the fix is not in the tooling but in the language: give agents a unit of work that is an ownership boundary, make the compiler know every state, every writer of it and every rule, and let a machine decide instead of a reviewer. Rust would be the first target, the way assembly is a C compiler’s target, and nobody would write it by hand.
The documents, in order
| when | document | what it holds |
|---|---|---|
| 25 Sept 2026 | experiments/history/parallel-first-demo/README.md and experiments/history/parallel-first-report.html | The first prototype, “Parallel-first: executable construction language, v0.2”: a source language inside a parallel! { … } macro, checked before bodies exist, bodies searched per unit, Rust emitted; the visual walkthrough of the first run. |
| 25 Sept 2026 | experiments/history/experiment-1/README.md | Experiment one and its results: agents given only the reference wrote correct programs on the first compile; the missing primitives each run exposed. |
| 25 Sept 2026 | experiments/history/pf/JEV-BRIEF.md | The concept stated in full for a language designer: what the language is for, what three experiments showed, the vocabulary to replace, the proposal of a small fixed core with a prelude written in the language. The closest thing to the original specification. |
| 25 Sept 2026 | experiments/history/pf/LANGUAGE.md, experiments/history/pf/README.md | The v0.3 language and its Rust front end. |
| 25 to 26 Sept 2026 | RESULTS.md, LANGUAGE.md | The results of every experiment through the thirty-unit shop, and the single-file reference the compiler and the writers were developed against. |
| 26 Sept 2026 | apps/COMPARISON.md | The same applications built the conventional way and this way, timed. |
| 27 Sept 2026 | docs/why.md, ROADMAP.md | What makes the language different, in two facts; and the roadmap as one list, with the language items in the order the self-hosted compiler needs. |
What each step established
- Experiment one: the agents were never the bottleneck; the language’s missing primitives were, and hard-coding them one by one is accretion, not a language. Hence the small fixed core with a prelude written in the language.
- Experiment seven: a frozen invariant caught a bug the plain-Rust arm shipped; the first time verification beat review.
- Experiments eight to ten: fifteen units in twenty seconds with zero edits, then thirty, with cheap writers; the cost moved to authoring the interface, which is where it still is.
- The tracker and the shop (26 Sept 2026): the conventional arm won on wall clock at CRUD size and lost at thirty units, where integration is serial; a single interface change costs exactly the contracts it reaches.
- 27 Sept 2026: the writer stage moved into the compiler, the language got views, deliveries, migrations, typed clients, partitioned verification, the sealed computation layer, and its own lexer and parser written in itself, held to the Rust ones on every file in this repository.
The name: the language was pf and then pf5 until 27 Sept 2026, when it became Vishy, after its author, with .vish files.